KR-X-AI commited on
Commit
600f091
·
verified ·
1 Parent(s): 1754a96

Upload tokenizer

Browse files
added_tokens.json CHANGED
@@ -1,25 +1,5 @@
1
  {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|PAD_TOKEN|>": 151665,
5
- "<|box_end|>": 151649,
6
- "<|box_start|>": 151648,
7
  "<|endoftext|>": 151643,
8
- "<|file_sep|>": 151664,
9
- "<|fim_middle|>": 151660,
10
- "<|fim_pad|>": 151662,
11
- "<|fim_prefix|>": 151659,
12
- "<|fim_suffix|>": 151661,
13
  "<|im_end|>": 151645,
14
- "<|im_start|>": 151644,
15
- "<|image_pad|>": 151655,
16
- "<|object_ref_end|>": 151647,
17
- "<|object_ref_start|>": 151646,
18
- "<|quad_end|>": 151651,
19
- "<|quad_start|>": 151650,
20
- "<|repo_name|>": 151663,
21
- "<|video_pad|>": 151656,
22
- "<|vision_end|>": 151653,
23
- "<|vision_pad|>": 151654,
24
- "<|vision_start|>": 151652
25
  }
 
1
  {
 
 
 
 
 
2
  "<|endoftext|>": 151643,
 
 
 
 
 
3
  "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
 
 
 
 
 
 
 
 
 
 
5
  }
special_tokens_map.json CHANGED
@@ -1,18 +1,7 @@
1
  {
2
  "additional_special_tokens": [
3
  "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
  ],
17
  "eos_token": {
18
  "content": "<|im_end|>",
@@ -22,7 +11,7 @@
22
  "single_word": false
23
  },
24
  "pad_token": {
25
- "content": "<|PAD_TOKEN|>",
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
 
1
  {
2
  "additional_special_tokens": [
3
  "<|im_start|>",
4
+ "<|im_end|>"
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
  "eos_token": {
7
  "content": "<|im_end|>",
 
11
  "single_word": false
12
  },
13
  "pad_token": {
14
+ "content": "<|endoftext|>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
3
- size 11422086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
3
+ size 11418266
tokenizer_config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
  "151643": {
@@ -25,190 +24,19 @@
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "151665": {
182
- "content": "<|PAD_TOKEN|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
  }
189
  },
190
  "additional_special_tokens": [
191
  "<|im_start|>",
192
- "<|im_end|>",
193
- "<|object_ref_start|>",
194
- "<|object_ref_end|>",
195
- "<|box_start|>",
196
- "<|box_end|>",
197
- "<|quad_start|>",
198
- "<|quad_end|>",
199
- "<|vision_start|>",
200
- "<|vision_end|>",
201
- "<|vision_pad|>",
202
- "<|image_pad|>",
203
- "<|video_pad|>"
204
  ],
205
  "bos_token": null,
206
- "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
207
  "clean_up_tokenization_spaces": false,
208
  "eos_token": "<|im_end|>",
209
  "errors": "replace",
210
  "model_max_length": 32768,
211
- "pad_token": "<|PAD_TOKEN|>",
212
  "padding_side": "left",
213
  "split_special_tokens": false,
214
  "tokenizer_class": "Qwen2Tokenizer",
 
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "151643": {
 
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  }
28
  },
29
  "additional_special_tokens": [
30
  "<|im_start|>",
31
+ "<|im_end|>"
 
 
 
 
 
 
 
 
 
 
 
32
  ],
33
  "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
  "clean_up_tokenization_spaces": false,
36
  "eos_token": "<|im_end|>",
37
  "errors": "replace",
38
  "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
  "padding_side": "left",
41
  "split_special_tokens": false,
42
  "tokenizer_class": "Qwen2Tokenizer",